📄 example2.html
字号:
<html>
<head>
<meta http-equiv="Keywords" content="neural, neural net, neural network, neural programming, mlp, backpropagation, back propagation, multilayer, perceptron, java, java package, example, class, training, train, incremental, batch, mini-batch, mini batch, generalized, modular, feed forward, feed, forward, cross validation, cross, validation, test, free, source, code">
<meta http-equiv="Content-Language" content="en-us">
<meta http-equiv="Description" content="This work is a java implementation of feed forward neural nets. Using this package, you can easily build and train multilayer, generalized feed forward, modular feed forward nets with any number of layers and any number of units.">
<title>Example 2 - FEED FORWARD NEURAL NETWORKS - A JAVA IMPLEMENTATION
v2.0</title>
<META HTTP-EQUIV="pragma" CONTENT="no-cache">
<META HTTP-EQUIV="Expires" CONTENT="Fri, 30 May 1980 01:00:00 GMT">
</head>
<body bgcolor="#e2e0e0" style="font-family: Verdana">
<div align="center">
<center>
<table width="90%" border="0" cellspacing="20" cellpadding="0" style="border-collapse: collapse" bordercolor="#111111">
<tr>
<td align="left">
<a href="index.html">Home</a></td>
</tr>
<tr>
<td align="left">
<b><font size="4"><a name="top"></a>FEED FORWARD NEURAL
NETWORK<span lang="tr">S</span> - A JAVA IMPLEMENTATION v2.0 </font></b>
<br><font size="5"><b>Example 2</b></font></td>
</tr>
<tr>
<td align="left">
In this example, we wish to resolve a classification
problem. We have data taken from a number of crabs. These
are measurements such as frontal lip, rear width, length,
sex etc. We create and train a net which be able to
determine the sex of a crab using measurements.<br>
<br>
- Create a multilayer perceptron with four layers: One input
layer with seven units; two hidden layers each with ten
neurons (tanh activation function); one output layer with
one neuron (tanh function). Here all neurons will be
connected to all neurons in the next layer.<br>
- Save the configuration of the net.<br>
- Create three pattern sets with 7 input and 1 output
values. First create a pattern set for training, then create
a pattern set for cross validation and then create a pattern
set for testing.<br>
- Show the error ratio (crossvalerror) before training.<br>
- Train the net using mini batch training, until
crossvalerror < 0.02, so that it learns how to distinguish a
female crab by using some measurements (alternatively you
can use incremental training). <br>
- Finally, check the error using test data.<br>
- Now that the training is over, save the weights of the
net.<br>
- Clean up the objects.<br>
- Recreate the net using previously saved configuration and
weig<span lang="tr">h</span>ts.<br>
- Test it.<br>
<br>
training data are from a tutorial of the "NeuroSolutions"
software<br>
<a href="http://www.neurosolutions.com/">
http://www.neurosolutions.com/</a></td>
</tr>
<tr>
<td align="left">
<a href="index.html">Home</a></td>
</tr>
</table>
</center>
</div>
</body>
</html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -